# Characterizing Uncertainty in the Visual Text Analysis Pipeline

arXiv: https://arxiv.org/abs/2209.13498 · HTML: https://mlsanity.com/paper/2209.13498/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 36 references that are in the map.
- First posted on arXiv 22 Sep 2022.

## Builds on (most cited first, 4 of 4)

- [Quantifying Uncertainties in Natural Language Processing Tasks](https://mlsanity.com/paper/1811.07253/) (2018)
- [Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language](https://mlsanity.com/paper/2207.06897/) (2022)
- [Why Authors Don't Visualize Uncertainty](https://mlsanity.com/paper/1908.01697/) (2019)
- [ClioQuery: Interactive Query-Oriented Text Analytics for Comprehensive Investigation of Historical News Archives](https://mlsanity.com/paper/2204.04694/) (2022)

## Built on by (most cited first, 1 of 1)

- [LayerFlow: Layer-wise Exploration of LLM Embeddings using Uncertainty-aware Interlinked Projections](https://mlsanity.com/paper/2504.10504/) (2025)

## Abstract (arXiv)

Current visual text analysis approaches rely on sophisticated processing pipelines. Each step of such a pipeline potentially amplifies any uncertainties from the previous step. To ensure the comprehensibility and interoperability of the results, it is of paramount importance to clearly communicate the uncertainty not only of the output but also within the pipeline. In this paper, we characterize the sources of uncertainty along the visual text analysis pipeline. Within its three phases of labeling, modeling, and analysis, we identify six sources, discuss the type of uncertainty they create, and how they propagate.